diff --git a/number_recoginition_capstone.ipynb b/number_recoginition_capstone.ipynb index 4808f15..39e8253 100644 --- a/number_recoginition_capstone.ipynb +++ b/number_recoginition_capstone.ipynb @@ -3532,58 +3532,6 @@ "img = Image.open('no_3.png')" ] }, - { - "cell_type": "code", - "execution_count": 17, - "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "^C\n", - "Collecting package metadata (current_repodata.json): ...working... done\n", - "Solving environment: ...working... failed with initial frozen solve. Retrying with flexible solve.\n", - "Collecting package metadata (repodata.json): ...working... done\n", - "Solving environment: ...working... failed with initial frozen solve. Retrying with flexible solve.\n" - ] - }, - { - "name": "stderr", - "output_type": "stream", - "text": [ - "\n", - "PackagesNotFoundError: The following packages are not available from current channels:\n", - "\n", - " - cv2\n", - " - pil\n", - "\n", - "Current channels:\n", - "\n", - " - https://repo.anaconda.com/pkgs/main/win-64\n", - " - https://repo.anaconda.com/pkgs/main/noarch\n", - " - https://repo.anaconda.com/pkgs/r/win-64\n", - " - https://repo.anaconda.com/pkgs/r/noarch\n", - " - https://repo.anaconda.com/pkgs/msys2/win-64\n", - " - https://repo.anaconda.com/pkgs/msys2/noarch\n", - " - https://conda.anaconda.org/conda-forge/win-64\n", - " - https://conda.anaconda.org/conda-forge/noarch\n", - "\n", - "To search for alternate channels that may provide the conda package you're\n", - "looking for, navigate to\n", - "\n", - " https://anaconda.org\n", - "\n", - "and use the search bar at the top of the page.\n", - "\n", - "\n" - ] - } - ], - "source": [ - "!conda install cv2 PIL\n" - ] - }, { "cell_type": "code", "execution_count": 26, @@ -3632,25 +3580,14 @@ }, { "cell_type": "code", - "execution_count": 37, + "execution_count": 44, "metadata": {}, "outputs": [ - { - "ename": "TypeError", - "evalue": "'AxesSubplot' object is not subscriptable", - "output_type": "error", - "traceback": [ - "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[1;31mTypeError\u001b[0m Traceback (most recent call last)", - "\u001b[1;32m\u001b[0m in \u001b[0;36m\u001b[1;34m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mfig\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msubplots_adjust\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mhspace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0.4\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mwspace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m0.2\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\u001b[1;33m \u001b[0maxes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msqueeze\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmy_img\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 7\u001b[0m \u001b[0maxes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_xaxis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_visible\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 8\u001b[0m \u001b[0maxes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_yaxis\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_visible\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n", - "\u001b[1;31mTypeError\u001b[0m: 'AxesSubplot' object is not subscriptable" - ] - }, { "data": { - "image/png": "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\n", + "image/png": "iVBORw0KGgoAAAANSUhEUgAABdoAAAJXCAYAAACE++a2AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8QVMy6AAAACXBIWXMAAAsTAAALEwEAmpwYAAAxCklEQVR4nO3de7zlZV33//eH2TNyUgQZkDkxYkKI5ahAUGYq/Rwh0ezgqTvJTOJOzSzrNvLOyvLQ3elWK6M8UKGSeSIPjN5illkih8HEJBEcYIbDIAgMhDOzuX5/rDW0ZzN7Zs++Zs+aPTyfj8c8Zq+9vvtan/WdNTq89ndfq1prAQAAAAAAZmafUQ8AAAAAAABzmdAOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWjnQamqxqtqdVVdWVVXVNUvV9U+w/uOr6q3TmONLwx/X15VL9rOcWdU1deHv87Ydc8CAAAAANgTVGtt1DPAbldVG1prBw4/PizJe5P8S2vt9TNY66lJXtNae9Y27jskySVJjk/Sklya5EmttdtnPj0AAAAAsCdxRTsPeq21W5KcmeQVNfDUqvpYklTVwqr6dFVdVlV/UVVrqurQ4X0bhku8OckPDq+Qf/Wk5Vcm+XRr7bZhXP90kmfunmcGAAAAAOwOQjskaa1dk8Hfh8Mm3fX6JBe11p6Y5MNJlm3jy1+b5J9baytaa3886b7FSa6fcPuG4ecAAAAAgL3E2KgHgD1IbeNzT07y3CRprV1YVTu75cu21rRfEwAAAADsRVzRDkmq6qgk40lumXxX59I3JFk64faSJOs61wQAAAAA9iBCOw96VbUwyTuSvL098N2BP5/kecPjnpHk4G0scVeSh06x/Kokz6iqg6vq4CTPGH4OAAAAANhL2DqGB6v9qmp1kvlJNif5myR/tI3jfjvJ+6rq+Uk+l+TGDML6RF9Osrmqrkjynon7tLfWbquqNyT50vBTv9Nau22XPhMAAAAAYKTqgRfwAltU1UOSjLfWNlfVyUn+vLW2YsRjAQAAAAB7EFvHwPYtS/Kl4dXqb03yshHPAwAADwpVtWH4Xko9a7ynqn53mscur6pWVWPD25+sqjN6Hn/C2j9YVVdNuP3NqvrhXbH2cL0rq+qpu2q93amqnlpVN0zz2N+qqr+d7ZmmeOyt5pzpOZ/8WgBg7yG0w3a01r7eWntCa+3xrbUTWmtf2vFXAQDAnqGqXlRVlwyj9Y3DePzkaX5tq6rvmu0Zp9JaO7C1ds0IH//U1tq5OzpuOueptfbPrbVjdsVc2/rmQWvtuNbaP+6K9Xfw2K2qbt7yzYjh58aq6paqelD9uPx0z/nk18eufC1M47HPqaqrquq+qvqZbdz/6qq6qaruqKp3DX+iG4AZEtoBAAD2QlX1y0n+JMkbkxyewU9r/lmS54xwrB2aGHH3Bnvb80ny7SSnTrh9WpLbRzPKzFXVvFHPsBtckeQXklw2+Y6qWpnktUlOSbI8yVEZvEcZADMktAMAAOxlquqgJL+T5OWttQ+11u5urW1qrf1Da+1Xh8ecWFX/WlXfHl7t/vaqWjC875+GS10xvBr++cPPP6uqVg+/5gtV9b0THvOJVXV5Vd1VVR+oqvMnXnldVS+rqqur6raquqCqFk24r1XVy6vq60m+PuFz3zX8eL+q+sOqWjO8+vbzVbXf8L4PTLgq95+q6rhpnqN5VfUHVXVrVV2T5Ecm3f+PVfVzw4+/q6o+N3yMW6vq/KnO05YtRqrqf1XVTUnePcX2KCdU1Ver6vaqendV7Ttc82eq6vOTZmnDGc5M8lNJfm34eP8wvP/+rWiq6iFV9SdVtW7460+2XKk8YbZfGV6FfmNVvWQ652uCv0ny4gm3X5zkryfNu2j4Z3zb8M/8ZRPu2294Vf7tVfXVJCds42s/WFXrq+raqvrF6Qw14bmdPfwz+mZV/dSE+99TVX9eVZ+oqruTPG17jzWNOSee83nDx/3G8PV/aVUt3d7rY8I6xw5fa9+uwXY0z540859W1ceH636xqh49nfORJK21P22tfSbJvdu4+4wk72ytXdlauz3JG5L8zHTXBuCBhHYAAIC9z8lJ9k3y4e0cM57k1UkOHR5/SgZXv6a19pThMY8fbuFyflU9Mcm7kvx8kkck+YskFwzD7oLhY70nySFJ3pfkuVseqKqenuRNSZ6X5Igka5K8f9I8P5rk+5I8dhuz/kGSJyX5/uH6v5bkvuF9n0zymCSHZXDl7nnbec4TvSzJs5I8IcnxSX5iO8e+IcmnkhycZEmStyXbPk/D248cznlkkjOnWPOnkqxM8ugkRyd53Y4Gbq2dk8Hz+/3h452+jcN+I8lJSVYkeXySEyet/cgkByVZnOSlSf60qg7e0WNP8JEkT6mqh1fVw5P8YJKPTjrmfUluSLIog/P6xqo6ZXjf6zN4zo/O4Pnfvw9+Ve2T5B8yuBJ7cQavyV+qwdXX0/HIDF7Pi4frnlNVE7dpeVGS30vy0CRf2MFjTTnnNvxykhdmcHX/w5L8bJJ7tvP62PJ85w9n+FQGr99XJjlv0swvzOBK84OTXD2cf8vXf6yqXruDczKV4zJ47ltckeTwqnrEDNcDeNAT2gEAAPY+j0hya2tt81QHtNYuba39W2ttc2vtmxmE8x/azpovS/IXrbUvttbGh/uXfyeDqHtSkrEkbx1eOf+hJBdP+NqfSvKu1tplrbXvJPn1JCdX1fIJx7yptXZba+2/Jj7oML7+bJJXtdbWDh/7C8N10lp7V2vtruHt30ry+Bpc0b8jz0vyJ62161trt2XwjYCpbMogmi9qrd3bWvv8do5NBt8EeH1r7TuTn88Eb5/w2L+XQVDdFX4qye+01m5pra3PINL+9IT7Nw3v39Ra+0SSDUl2Zs/wezOIw89P8oIkF2TCFdNVtTTJk5P8r+G5Wp3krybM8Lwkvzf8s74+yVsnrH1CkoWttd9prW0c7tH/l8PHma7/PTzvn0vy8eHjbfHR1tq/tNbuS/I9O3is7c052c8leV1r7ao2cEVr7VvTmPWkJAcmefNwhouSfCxbvxY+1Fq7ePh3+bwMvoGSJGmtPau19uZpPM62HJjkjgm3t3z80BmuB/CgJ7QDAADsfb6V5NDazv7gVXX08IrYm6rqzgz2cj90O2semeRXhltcfLuqvp1kaQZXLS9Ksra1NvENMa+f8PGiDK5iT5K01jYMZ1w8xfETHZrB1fnf2MZzmFdVbx5u2XFnkm9O+JodWTTpMddMdWAGV9BXkouH23v87A7WXt9a29Z2HRNNfuxFUx24k7Y619tY+1uTvgFzTwbRdWf8dQZbxjxg25jhY93WWrtr0gyLJ9w/1Xk/MsmiSa+xszN4j4HpuL21dvektSc+94mPu6PH2pnXx9Js4/U5DYuSXD8M/xMfZ+Lfi5smfDyTP6upbMjg6vsttnx81zaOBWAahHYAAIC9z79mcJXxj27nmD9P8rUkj2mtPSyDyFjbOf76DK7wffiEX/u31t6X5MYki6tq4tcvnfDxugzCZpKkqg7I4Kr7tROOmRjpJ7p1+Fy2tTf1izJ4c9cfzmA7lOVbHmI7z2OLGyfNuGyqA1trN7XWXtZaW5TB1jl/VsP946f6kmk8/uTHXjf8+O4k+2+5o6oeuZNrb3WuJ629q/xzBlsAHZ5k8tX965IcUlUTr4xelv/+s97eeb8+ybWTXmMPba2dNs25Dh6+tiauPfG5T/5G0PYea9qvj+Fa0947fYJ1SZYOf2pj4uOsneL4XenKDLYW2uLxSW6e5pX4AGyD0A4AALCXaa3dkeQ3M9h/+0erav+qml9Vp1bV7w8Pe2iSO5NsqKrvTvI/Jy1zc5KjJtz+yyRnVdX31cABVfUjw6D6rxns+f6KqhqrqudksDf4Fu9N8pKqWlGDN+Z8Y5IvDres2dFzuS+DveH/aPjmlfOq6uThOg/NYPuab2UQp984/bOUv0vyi1W1ZLhH+ZR7XVfVT1bVkuHN2zMItuPD25PP03S9fPjYh2TwTY4t+3dfkeS44bnaN4PtcCba0eO9L8nrqmphVR2awevgb2cw35SGP7lwepJnT/ophgy3WflCkjdV1b41eMPcl+a/987/uyS/XlUHD8/pKyd8+cVJ7qzBG8nuN/yzflxVbfVGpDvw21W1oKp+MIM9+D8wxXE7eqztzTnZXyV5Q1U9Zvh343sn7HW+vT+vL2bwjZVfG/79fGoG53Xy+xfMyPA87JvBN57mD/88tnSgv07y0qp67PD1/7oM3mMBgBkS2gEAAPZCrbU/yuBNGl+XZH0GV92+IoM3s0yS12RwRfhdGUT08yct8VtJzh1uq/G81tolGezT/vYMYvPVSX5m+Fgbk/xYBkH120n+RwZ7TW/ZR/0zSf53kg9mcKXwo7Nz+26/Jsm/J/lSktuSvCWD/5796wy22lib5KtJ/m0n1vzLJKsyCNuXJfnQdo49IckXq2pDBnuSv6q1du3wvt/KhPO0E4//3gzeBPOa4a/fTZLW2n8m+Z0k/y/J1/PAK8bfmeSxw8f7yDbW/d0klyT5cgbn7LIta+9IVZ1dVZ+czrGttStba1dOcfcLM/jpgnUZvEnu61trnx7e99sZ/Jldm8Hz/5sJa45nEJpXDO+/NYOIPZ0995PBNiu3Dx/3vCRntda+NsX8O3qsKefchj/KIMx/KoNvXr0zyX7D+34rU7w+hn9vnp3k1OHj/1mSF08182RV9cmqOns7h3wqyX9l8CbC5ww/fsrwsS9M8vtJPjt8nmsyeANYAGaoJn3zGQAAALpV1ReTvKO19u5Rz8Leb3g1+N+21pbs4FAAmBWuaAcAAKBbVf1QVT1yuHXMGUm+N8mFo54LAGB3mPId6AEAAGAnHJPB9hkHJvlGkp9ord042pEAAHYPW8cAAAAAAEAHW8cAAAAAAECHndo65tBD5rXlS+fP1iwAAFv55vWbcutt4zXV/Yceemhbvnz5bpwIAACAB7NLL7301tbawsmf36nQvnzp/Fy8aumumwoAYDtOXHn9du9fvnx5Lrnkkt00DQAAAA92VbVmW5+3dQwAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQCYdS999c155OOuzfc+9bpt3t9ay6tetz5Hn7wmK55+XS778r27eUIAAACYOaEdAJh1ZzzvYfnEe4+Y8v5PXnRPvn7Nplz1hWV5x/85LC9/7frdOB0AAAD0EdoBgFn3lJP3yyEHz5vy/gsuvDs//ZMPTVXlpCftm2/feV9uvHnzbpwQAAAAZm5s1AMAAKy9aXOWLvrvf5YsOWIsa2/cdmivqjOTnJkky5Yt2y3zAQAA7A7LX/vxUY8wEt9884+MeoRurmgHAEautQd+rmqqY9s5rbXjW2vHL1y4cHYHAwAAgGkQ2gGAkVtyxFiuX/ffV7DfcOPmLHqkH7wDAABgbhDaAYCRO33lAfmbD9yV1lr+7dJ7c9BD98kRhwvtAAAAzA3+CxYAmHUv+p835XNf+K/cett4lj3x2rz+NY/Ipk2D/WLOOuOgnHbK/vnkZ+7J0Sevyf777ZN3/vFhI54YAAAApk9oBwBm3Xv//JHbvb+q8vY3LUxiz3UAAADmHlvHAAAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBgb9QCwq61ctGLUI7ANq9atHvUIAAAAADArXNEOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKDD2KgHgD3RqnWru9e4576N3Ws8d8mJ3WvsKc6++Xu713jj4V/eBZMAAAAAwK7linYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB3GRj0ATHTacU/rXmPVus/ugkn67b/Pgu41Vq1b3T/IHmLl4id0r/GEl/9C9xqXn/1n3WsAAAAAwESuaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAMCsu/Ciu3Psk9fk6JPX5C1vu/0B999x53ie/eJ1ecIp1+V7fui6vPv9d45gSgAAAJgZoR0AmFXj4y2vPHt9Pn7eonzlc8vy/o/cla9etXGrY/7s3XfksUcvyOWfWZaLPrg4v/rbt2bjxjaiiQEAAGDnCO0AwKy6+PJ78+jl83PUkfOzYEHl+c85MBes2rDVMVXJXRvuS2stG+65L4c8fF7GxkY0MAAAAOwkoR0AmFVrbxrP0sXz77+9+IixrL1pfKtjXv6zD8/Xvr4pS1Z8M49/2nX54zccmn32qW2uV1VnVtUlVXXJ+vXrZ3V2AAAAmA6hHQCYVW0bO8DUpIa+6h/vyeOPW5AbVi/PZf9vaX7x7PW58677plivndNaO761dvzChQtnYWIAAADYOUI7ADCrlhwxL9ev3XT/7bU3bs6iw+dtdcx73n9nnnvagamqfNejFuRRy+bna1dvnLwUAAAA7JGEdgBgVp2wYt9cfe2mXHvdpmzc2HL+Rzfk9JUHbHXMssVjuejz9yRJbl6/OVd9Y2OOWjZ/W8sBAADAHsfbjAEAs2psrPLWNy7MqS9cl/Hxlpe84GE57piH5B3n3pEkOeuMg/K6Vx+Sl7zq5jz+adelteRNv3FoDn3EvB2sDAAAAHsGoR0AmHWnnXJATjtl66vYzzrjoPs/XvTIsaw6f/HuHgsAAAB2CaGdPcr47bePegRmyaq1l3evcdSHT+xeY+WiFd1rrFq3unsNAAAAAPYe9mgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBhbNQDAEzXNc/9i/5Fntu/xMpFK7rXmHfsY7rX+MRnPtC9BgAAAAD9XNEOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKDD2KgHAJhrVq1b3b3GykX9cwAAAACwZ3BFOwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADmOjHgAmWrVu9ahHgN1iV7zWVy5asUfMAQAAAPBg54p2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdxkY9AHuPoz93Rvca//lD5+6CSQAAAAAAdh9XtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6DA26gHYezzqhVf0L7Kufwl4sNj46SN3wSqrd8EaAAAAAA9urmgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwBm3YUX3Z1jn7wmR5+8Jm952+3bPOYfv3BPnvjD1+V7fui6PO25N+zmCQEAAGDmxkY9AACwdxsfb3nl2euz6vzFWXLEWL7v1Otz+jMOyGOPWXD/Md++YzyveO36fOK9i7JsyfzccuvmEU4MAAAAO8cV7QDArLr48nvz6OXzc9SR87NgQeX5zzkwF6zasNUx7/vwhjz3tAOzbMn8JMlhh7oWAAAAgLlDaAcAZtXam8azdPH8+28vPmIsa28a3+qY//zGxtx+x315+o/dkBOecX3++u/unHK9qjqzqi6pqkvWr18/a3MDAADAdLlcDACYVa098HNVW9/ePJ5c9uV78+kPLM5//VfLD5x+Q0560r5TrNfOSXJOkhx//PHbWB0AAAB2L6EdAJhVS46Yl+vXbrr/9tobN2fR4fMmHTOWQw/ZPwfsv08O2D/5wZP2zRVf3bi7RwUAAIAZsXUMADCrTlixb66+dlOuvW5TNm5sOf+jG3L6ygO2OubZKw/I5794bzZvbrnnnvty8WXfybGPmT/FigAAALBncUU7ADCrxsYqb33jwpz6wnUZH295yQseluOOeUjece4dSZKzzjgoxx69ICuftn9WPP267LNP5aUvelge990PGfHkAAAAMD1CO8Ac9dnjPtq9xspFK7rXWLVudfca7P1OO+WAnHbK1lexn3XGQVvdfs0vHJzX/MLBu3MsAAAA2CVsHQMAAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBgFl34UV359gnr8nRJ6/JW952+5THfWn1vZm/+Or8/cc27MbpAAAAoI/QDgDMqvHxlleevT4fP29RvvK5ZXn/R+7KV6/auM3jfv13v5VnPHX/EUwJAAAAMye0AwCz6uLL782jl8/PUUfOz4IFlec/58BcsOqBV6y//Z135Md+5IAcdui8EUwJAAAAMye0AwCzau1N41m6eP79txcfMZa1N41vfcyNm/ORT27Iz7/4oB2uV1VnVtUlVXXJ+vXrd/m8AAAAsLOEdgBgVrX2wM9VbX371b+5Pm963aGZN68eePAD1mvntNaOb60dv3Dhwl00JQAAAMzc2KgHAAD2bkuOmJfr1266//baGzdn0eFbbw9z6RXfyYvOuilJcutt4/nkZ+7JmB1kAAAAmCNc0Q4AzKoTVuybq6/dlGuv25SNG1vO/+iGnL7ygK2O+cbFy3PNlwa/fvxZB+btb16YHz31wBFNDAAAADvHFe0AwKwaG6u89Y0Lc+oL12V8vOUlL3hYjjvmIXnHuXckSc46Y8f7sgMAAMCeTGgHAGbdaacckNNO2foq9qkC+7v/7+G7YyQAAADYZWwdAwAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0GBv1AOw9Vq1b3b3GUR/8+e41rvnxv+heAx4s7j39xF2wyupdsAYAAADA3OWKdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHcZGPQBM9N2/8R/9i/x4/xIwF6xc/ITuNT639pxdMAkAAADAg5sr2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBgb9QAw0Se+9k/da6xctKJ7jVXrVnevAdvzzGXHd6+x/Ivzd8EkAAAAAPRyRTsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5jox4AdrVV61Z3r7Fy0YruNXaFDc87qXuNbz2uutdo/Uvk0H9v3Wvsiudy5G/+a/cau8LjLr2ve40/PGLPeC4AAAAAD3auaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgDMugsvujvHPnlNjj55Td7yttsfcP95H7wrK55+XVY8/bo8+fQbcsWV3xnBlAAAADAzY6MeAADYu42Pt7zy7PVZdf7iLDliLN936vU5/RkH5LHHLLj/mEctG8tnP7Q4Bz98Xj75mbtz1q/ekn/9xNIRTg0AAADT54p2AGBWXXz5vXn08vk56sj5WbCg8vznHJgLVm3Y6pjvP2G/HPzweUmSk560b264cfMoRgUAAIAZEdoBgFm19qbxLF08//7bi48Yy9qbxqc8/l3vuzPPfPoBU95fVWdW1SVVdcn69et36awAAAAwE7aOAQBmVWsP/FzVto/97L/ck3e9987800eXbGe9dk6Sc5Lk+OOP38bqAAAAsHsJ7bANq9atHvUIQ6tHPcDe5+dGPQA8+Cw5Yl6uX7vp/ttrb9ycRYfPe8BxX/7qd3Lmr9ySj5+3KI845IH3AwAAwJ7K1jEAwKw6YcW+ufraTbn2uk3ZuLHl/I9uyOkrt94a5robNuUnXnpTzn3b4Tn60QumWAkAAAD2TK5oBwBm1dhY5a1vXJhTX7gu4+MtL3nBw3LcMQ/JO869I0ly1hkH5Q1/fHu+dft4XvHrgz3Xx+ZVLl61dJRjAwAAwLQJ7QDArDvtlANy2ilbX8V+1hkH3f/xX/7hYfnLPzxsd48FAAAAu4StYwAAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAAAAAAHQQ2gEAAAAAoIPQDgAAAAAAHYR2AAAAAADoILQDAAAAAEAHoR0AAAAAADoI7QAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAB6EdAAAAAAA6CO0AAAAAANBBaAcAAAAAgA5COwAAAAAAdBDaAQAAAACgg9AOAAAAAAAdhHYAAAAAAOggtAMAAAAAQAehHQAAAAAAOgjtAAAAAADQQWgHAAAAAIAOQjsAMOsuvOjuHPvkNTn65DV5y9tuf8D9rbW86nXrc/TJa7Li6dflsi/fO4IpAQAAYGaEdgBgVo2Pt7zy7PX5+HmL8pXPLcv7P3JXvnrVxq2O+eRF9+Tr12zKVV9Ylnf8n8Py8teuH9G0AAAAsPOEdgBgVl18+b159PL5OerI+VmwoPL85xyYC1Zt2OqYCy68Oz/9kw9NVeWkJ+2bb995X268efOIJgYAAICdU6216R9ctT7JmtkbBwDYCx2c5GH5739DHJLkwCTXTTjmu5LclGRLgT86yQ1JFrbWFk5crKrOTHLm8OYxSa6anbH3GocmuXXUQ8xBztvMOXcz47zNjPM2c87dzDhvM+O8zYzzNnPO3cw4b9Nz5OT/Tk12MrQDAOysqvrJJCtbaz83vP3TSU5srb1ywjEfT/Km1trnh7c/k+TXWmuXjmLmvUlVXdJaO37Uc8w1ztvMOXcz47zNjPM2c87dzDhvM+O8zYzzNnPO3cw4b31sHQMAzLYbkiydcHtJknUzOAYAAAD2SEI7ADDbvpTkMVX1qKpakOQFSS6YdMwFSV5cAycluaO1duPuHhQAAABmYmzUAwAAe7fW2uaqekWSVUnmJXlXa+3KqjpreP87knwiyWlJrk5yT5KXjGrevdA5ox5gjnLeZs65mxnnbWact5lz7mbGeZsZ521mnLeZc+5mxnnrYI92AAAAAADoYOsYAAAAAADoILQDAAAAAEAHoR0AYC9VVc+sqquq6uqqeu2o55kLqupdVXVLVX1l1LPMJVW1tKo+W1X/UVVXVtWrRj3TXFBV+1bVxVV1xfC8/faoZ5pLqmpeVV1eVR8b9SxzSVV9s6r+vapWV9Ulo55nrqiqh1fV31fV14b/W3fyqGeaC6rqmOFrbcuvO6vql0Y911xQVa8e/n/DV6rqfVW176hnmguq6lXDc3al19r2bevfvVV1SFV9uqq+Pvz94FHOONcI7QAAe6GqmpfkT5OcmuSxSV5YVY8d7VRzwnuSPHPUQ8xBm5P8Smvt2CQnJXm519u0fCfJ01trj0+yIskzq+qk0Y40p7wqyX+Meog56mmttRWtteNHPcgc8n+TXNha++4kj4/X3rS01q4avtZWJHlSBm96/+HRTrXnq6rFSX4xyfGttcclmZfkBaOdas9XVY9L8rIkJ2bw9/RZVfWY0U61R3tPHvjv3tcm+Uxr7TFJPjO8zTQJ7QAAe6cTk1zdWrumtbYxyfuTPGfEM+3xWmv/lOS2Uc8x17TWbmytXTb8+K4MAtTi0U6152sDG4Y35w9/tRGONGdU1ZIkP5Lkr0Y9C3u/qnpYkqckeWeStNY2tta+PdKh5qZTknyjtbZm1IPMEWNJ9quqsST7J1k34nnmgmOT/Ftr7Z7W2uYkn0vy3BHPtMea4t+9z0ly7vDjc5P86O6caa4T2gEA9k6Lk1w/4fYNET7ZDapqeZInJPniiEeZE4bbn6xOckuST7fWnLfp+ZMkv5bkvhHPMRe1JJ+qqkur6sxRDzNHHJVkfZJ3D7cr+quqOmDUQ81BL0jyvlEPMRe01tYm+YMk1yW5MckdrbVPjXaqOeErSZ5SVY+oqv2TnJZk6YhnmmsOb63dmAwupEhy2IjnmVOEdgCAvVNt43OulGVWVdWBST6Y5Jdaa3eOep65oLU2PtxSYUmSE4c/9s52VNWzktzSWrt01LPMUT/QWntiBluLvbyqnjLqgeaAsSRPTPLnrbUnJLk7tlPYKVW1IMmzk3xg1LPMBcN9sZ+T5FFJFiU5oKr+x2in2vO11v4jyVuSfDrJhUmuyGB7O9gthHYAgL3TDdn6Cp4l8SPHzKKqmp9BZD+vtfahUc8z1wy3ofjHeI+A6fiBJM+uqm9msC3W06vqb0c70tzRWls3/P2WDPbKPnG0E80JNyS5YcJPnPx9BuGd6Ts1yWWttZtHPcgc8cNJrm2trW+tbUryoSTfP+KZ5oTW2jtba09srT0lg21Rvj7qmeaYm6vqiCQZ/n7LiOeZU4R2AIC905eSPKaqHjW8iuwFSS4Y8UzspaqqMti7+D9aa3806nnmiqpaWFUPH368XwZh5WsjHWoOaK39emttSWtteQb/23ZRa82VntNQVQdU1UO3fJzkGRlstcB2tNZuSnJ9VR0z/NQpSb46wpHmohfGtjE747okJ1XV/sP/jz0l3oB3WqrqsOHvy5L8WLzudtYFSc4YfnxGko+OcJY5Z2zUAwAAsOu11jZX1SuSrEoyL8m7WmtXjnisPV5VvS/JU5McWlU3JHl9a+2do51qTviBJD+d5N+H+40nydmttU+MbqQ54Ygk51bVvAwugvq71trHRjwTe7fDk3x40O0yluS9rbULRzvSnPHKJOcNv3l9TZKXjHieOWO4V/b/l+TnRz3LXNFa+2JV/X2SyzLY+uTyJOeMdqo544NV9Ygkm5K8vLV2+6gH2lNt69+9Sd6c5O+q6qUZfMPnJ0c34dxTrdmqEwAAAAAAZsrWMQAAAAAA0EFoBwAAAACADkI7AAAAAAB0ENoBAAAAAKCD0A4AAAAAAB2EdgAAAAAA6CC0AwAAAABAh/8f64igFpvm8a8AAAAASUVORK5CYII=\n", "text/plain": [ - "
" + "
" ] }, "metadata": { @@ -3663,17 +3600,17 @@ "\n", "predict = model.predict(my_img)\n", "\n", - "fig, axes = plt.subplots(1, 1, figsize=(16, 12))\n", + "fig, axes = plt.subplots(1,2, figsize=(25, 10))\n", "fig.subplots_adjust(hspace=0.4, wspace=-0.2)\n", "\n", - "axes[0, 0].imshow(np.squeeze(my_img))\n", - "axes[0, 0].get_xaxis().set_visible(False)\n", - "axes[0, 0].get_yaxis().set_visible(False)\n", - "axes[0, 0].text(10., -1.5, f'Digit {0}')\n", + "axes[0].imshow(np.squeeze(my_img))\n", + "axes[0].get_xaxis().set_visible(False)\n", + "axes[0].get_yaxis().set_visible(False)\n", + "axes[0].text(10., -1.5, f'Digit {0}')\n", "for pred in predict:\n", - " axes[0, 1].bar(np.arange(len(pred)), pred)\n", - " axes[0, 1].set_xticks(np.arange(len(pred)))\n", - " axes[0, 1].set_title(f\"Categorical distribution. Model prediction: {np.argmax(pred)}\")" + " axes[1].bar(np.arange(len(pred)), pred)\n", + " axes[1].set_xticks(np.arange(len(pred)))\n", + " axes[1].set_title(f\"Categorical distribution. Model prediction: {np.argmax(pred)}\")" ] } ],